Intellectual Property India Publishes Patent Application for 'Counterfactual Based Gender Fairness Algorithm For Large Language Models' Filed by Tata Consultancy Services Limited

MUMBAI, India, Nov. 21 -- Intellectual Property India has published a patent application (202421039028 A) filed by Tata Consultancy Services Limited, Maharashtra, on May 17, 2024, for 'counterfactual based gender fairness algorithm for large language models.'

Inventor(s) include Paul, Bivek Benoy; Bansal, Krishna Kumar; Purushothaman, Anirudh Thenguvila; Kasiviswanathan, Selva Sarmila; and Balaji, Ramesh.

The application for the patent was published on Nov. 21, under issue no. 47/2025.

According to the abstract released by the Intellectual Property India: "Gender bias assessment techniques that are available currently only consider two 5 genders viz male and female and is not inclusive of lesbian, gay, bisexual, transgender and queer (LGBTQ) genders. Present disclosure provides method and system for assessing gender fairness of large language models (LLM). The system first receive context aware prompt comprising context and prompt and then converts names present in the context using name anonymization technique. The 10 system then convert many-to-many pronouns present in no-name-context into many to one pronouns which are then used to create counterfactual context for each gender pronoun group. Thereafter, system queries LLM with counterfactual prompt created using counterfactual context to obtain counterfactual response which is then used to create embedding data frame. Further, system trains Gaussian Mixture 15 Model using embedding data frame which is then utilized to calculate cluster distances. Finally, system assess gender bias based on cluster distances and predefined distance threshold."

Disclaimer: Curated by HT Syndication.